npm - omnilane - Versions diffs - 0.34.0 → 0.42.1 - Mend

omnilane 0.34.0 → 0.42.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (42) hide show

package/.claude-plugin/marketplace.json +4 -4
package/.claude-plugin/plugin.json +2 -2
package/CHANGELOG.md +71 -1
package/README.ja.md +63 -33
package/README.ko.md +63 -32
package/README.md +147 -86
package/README.zh-CN.md +61 -30
package/README.zh-TW.md +124 -75
package/VERSION +1 -1
package/config/aa-model-policy.json +3046 -0
package/docs/aa-model-coverage-2026-09-05.json +29204 -0
package/docs/completion-wakeup.md +126 -0
package/docs/model-capabilities-2026-09.md +380 -0
package/docs/native-executor.md +264 -0
package/docs/release-notes-0.42.1.md +32 -0
package/hooks/routing-instruction.md +101 -40
package/package.json +8 -2
package/plugin.json +2 -2
package/routing.local.yaml.example +8 -3
package/routing.yaml +16 -16
package/scripts/completion-wakeup.py +390 -0
package/scripts/configure.sh +4 -4
package/scripts/dispatch.sh +323 -32
package/scripts/doctor.sh +55 -1
package/scripts/jobs.sh +64 -17
package/scripts/lib/aa_policy.py +473 -0
package/scripts/lib/aa_retry.py +77 -0
package/scripts/lib/common.sh +106 -1
package/scripts/lib/job-worker.sh +314 -20
package/scripts/lib/live-protocol.sh +147 -2
package/scripts/lib/native.py +507 -0
package/scripts/lib/normalize-claude-stream.py +72 -0
package/scripts/lib/prepare-agy-mode.py +374 -0
package/scripts/release-audit.sh +103 -0
package/scripts/runners/run-claude.sh +81 -47
package/scripts/runners/run-codex-live.py +462 -0
package/scripts/runners/run-codex.sh +62 -3
package/scripts/runners/run-gemini.sh +85 -10
package/scripts/runners/run-grok-live.py +426 -0
package/scripts/runners/run-grok.sh +117 -6
package/scripts/runners/run-vote.sh +6 -3
package/skills/omnilane/SKILL.md +217 -81

package/config/aa-model-policy.json ADDED Viewed

@@ -0,0 +1,3046 @@
+{
+  "schema_version": 1,
+  "snapshot": {
+    "id": "aa-v4.2-2026-09-07-v1",
+    "benchmark": "Artificial Analysis Intelligence Index",
+    "benchmark_version": "4.2",
+    "as_of": "2026-09-07",
+    "timezone": "Asia/Taipei",
+    "frozen": true,
+    "approval": {
+      "status": "approved",
+      "scope": "model-governance-proposal-v2",
+      "source": "docs/model-governance-proposal.md",
+      "estimated_scores": "approved_provisional"
+    },
+    "automatic_refresh_grants_authority": false
+  },
+  "policy": {
+    "decision": "target_score <= min(caller_score, inherited_ceiling)",
+    "inherited_ceiling_required_for_child": true,
+    "root_ceiling": "verified_caller_score",
+    "same_score_allowed": true,
+    "unknown": "deny",
+    "missing_identity_field": "deny",
+    "missing_transport_mapping": "deny",
+    "snapshot_version_mismatch": "deny",
+    "family_only_lookup": "deny",
+    "display_grade_is_authority": false,
+    "score_field": "score",
+    "estimate_is_independent_measurement": false,
+    "identity_fields": [
+      "vendor",
+      "model",
+      "effort",
+      "reasoning",
+      "fallback"
+    ],
+    "null_identity_field": "literal_unspecified_in_evidence_not_wildcard",
+    "transport_mapping_requires_runtime_verification": true
+  },
+  "scored_configs": [
+    {
+      "id": "codex/gpt-6-astra",
+      "vendor": "codex",
+      "model": "gpt-6-astra",
+      "effort": "max",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-6-astra",
+      "score": 55,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-6-astra",
+        "https://artificialanalysis.ai/models/releases/gpt-6-astra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-6-astra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-6-astra-xhigh",
+      "vendor": "codex",
+      "model": "gpt-6-astra",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-6-astra-xhigh",
+      "score": 54,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-6-astra-xhigh",
+        "https://artificialanalysis.ai/models/releases/gpt-6-astra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-6-astra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-6-astra-high",
+      "vendor": "codex",
+      "model": "gpt-6-astra",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-6-astra-high",
+      "score": 53,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-6-astra-high",
+        "https://artificialanalysis.ai/models/releases/gpt-6-astra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-6-astra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-6-astra-medium",
+      "vendor": "codex",
+      "model": "gpt-6-astra",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-6-astra-medium",
+      "score": 52,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-6-astra-medium",
+        "https://artificialanalysis.ai/models/releases/gpt-6-astra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-6-astra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-6-astra-low",
+      "vendor": "codex",
+      "model": "gpt-6-astra",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-6-astra-low",
+      "score": 49,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-6-astra-low",
+        "https://artificialanalysis.ai/models/releases/gpt-6-astra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-6-astra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-6-astra-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-6-astra",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-6-astra-non-reasoning",
+      "score": 48,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-6-astra-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-6-astra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-6-astra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-sol",
+      "vendor": "codex",
+      "model": "gpt-5.6-sol",
+      "effort": "max",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-sol",
+      "score": 51,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-sol",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-sol"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-sol"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-sol-xhigh",
+      "vendor": "codex",
+      "model": "gpt-5.6-sol",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-sol-xhigh",
+      "score": 50,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-sol"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-sol"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-sol-high",
+      "vendor": "codex",
+      "model": "gpt-5.6-sol",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-sol-high",
+      "score": 48,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-sol-high",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-sol"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-sol"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-sol-medium",
+      "vendor": "codex",
+      "model": "gpt-5.6-sol",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-sol-medium",
+      "score": 46,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-sol-medium",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-sol"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-sol"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-sol-low",
+      "vendor": "codex",
+      "model": "gpt-5.6-sol",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-sol-low",
+      "score": 41,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-sol-low",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-sol"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-sol"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-sol-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-5.6-sol",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-sol-non-reasoning",
+      "score": 33,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-sol"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-sol"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-terra",
+      "vendor": "codex",
+      "model": "gpt-5.6-terra",
+      "effort": "max",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-terra",
+      "score": 47,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-terra",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-terra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-terra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-terra-xhigh",
+      "vendor": "codex",
+      "model": "gpt-5.6-terra",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-terra-xhigh",
+      "score": 44,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-terra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-terra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-terra-high",
+      "vendor": "codex",
+      "model": "gpt-5.6-terra",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-terra-high",
+      "score": 41,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-terra-high",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-terra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-terra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-terra-medium",
+      "vendor": "codex",
+      "model": "gpt-5.6-terra",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-terra-medium",
+      "score": 37,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-terra-medium",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-terra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-terra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-terra-low",
+      "vendor": "codex",
+      "model": "gpt-5.6-terra",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-terra-low",
+      "score": 32,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-terra-low",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-terra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-terra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-terra-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-5.6-terra",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-terra-non-reasoning",
+      "score": 26,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-terra"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-terra"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-luna",
+      "vendor": "codex",
+      "model": "gpt-5.6-luna",
+      "effort": "max",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-luna",
+      "score": 43,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-luna",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-luna"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-luna"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-luna-xhigh",
+      "vendor": "codex",
+      "model": "gpt-5.6-luna",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-luna-xhigh",
+      "score": 42,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-luna"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-luna"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-luna-high",
+      "vendor": "codex",
+      "model": "gpt-5.6-luna",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-luna-high",
+      "score": 37,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-luna-high",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-luna"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-luna"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-luna-medium",
+      "vendor": "codex",
+      "model": "gpt-5.6-luna",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-luna-medium",
+      "score": 30,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-luna-medium",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-luna"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-luna"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-luna-low",
+      "vendor": "codex",
+      "model": "gpt-5.6-luna",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-luna-low",
+      "score": 26,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-luna-low",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-luna"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-luna"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-6-luna-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-5.6-luna",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-6-luna-non-reasoning",
+      "score": 19,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-5-6-luna"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.6-luna"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-5",
+      "vendor": "codex",
+      "model": "gpt-5.5",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-5",
+      "score": 46,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-5",
+        "https://artificialanalysis.ai/models/releases/gpt-5-5"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-5-high",
+      "vendor": "codex",
+      "model": "gpt-5.5",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-5-high",
+      "score": 44,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-5-high",
+        "https://artificialanalysis.ai/models/releases/gpt-5-5"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-5-medium",
+      "vendor": "codex",
+      "model": "gpt-5.5",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-5-medium",
+      "score": 42,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-5-medium",
+        "https://artificialanalysis.ai/models/releases/gpt-5-5"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-5-low",
+      "vendor": "codex",
+      "model": "gpt-5.5",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-5-low",
+      "score": 35,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-5-low",
+        "https://artificialanalysis.ai/models/releases/gpt-5-5"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-5-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-5.5",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-5-non-reasoning",
+      "score": 27,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-5-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-5-5"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-4",
+      "vendor": "codex",
+      "model": "gpt-5.4",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-4",
+      "score": 43,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-4",
+        "https://artificialanalysis.ai/models/releases/gpt-5-4"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.4"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-4-low",
+      "vendor": "codex",
+      "model": "gpt-5.4",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-4-low",
+      "score": 32,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-4-low",
+        "https://artificialanalysis.ai/models/releases/gpt-5-4"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.4"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-4-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-5.4",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-4-non-reasoning",
+      "score": 21,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-4-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-5-4"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.4"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-4-mini",
+      "vendor": "codex",
+      "model": "gpt-5.4-mini",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-4-mini",
+      "score": 32,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-4-mini",
+        "https://artificialanalysis.ai/models/releases/gpt-5-4-mini"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.4-mini"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-4-mini-medium",
+      "vendor": "codex",
+      "model": "gpt-5.4-mini",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-4-mini-medium",
+      "score": 23,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-4-mini-medium",
+        "https://artificialanalysis.ai/models/releases/gpt-5-4-mini"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.4-mini"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "codex/gpt-5-4-mini-non-reasoning",
+      "vendor": "codex",
+      "model": "gpt-5.4-mini",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "gpt-5-4-mini-non-reasoning",
+      "score": 11,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning",
+        "https://artificialanalysis.ai/models/releases/gpt-5-4-mini"
+      ],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gpt-5.4-mini"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-fable-5-1",
+      "vendor": "claude",
+      "model": "claude-fable-5-1",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": "default",
+      "aa_slug": "claude-fable-5-1",
+      "score": 57,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-fable-5-1"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-fable-5-1"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-fable-5-1-xhigh",
+      "vendor": "claude",
+      "model": "claude-fable-5-1",
+      "effort": "xhigh",
+      "reasoning": "adaptive",
+      "fallback": "default",
+      "aa_slug": "claude-fable-5-1-xhigh",
+      "score": 54,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-fable-5-1-xhigh"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-fable-5-1"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-fable-5-1-high",
+      "vendor": "claude",
+      "model": "claude-fable-5-1",
+      "effort": "high",
+      "reasoning": "adaptive",
+      "fallback": "default",
+      "aa_slug": "claude-fable-5-1-high",
+      "score": 52,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-fable-5-1-high"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-fable-5-1"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-fable-5-1-medium",
+      "vendor": "claude",
+      "model": "claude-fable-5-1",
+      "effort": "medium",
+      "reasoning": "adaptive",
+      "fallback": "default",
+      "aa_slug": "claude-fable-5-1-medium",
+      "score": 50,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-fable-5-1-medium"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-fable-5-1"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-fable-5-1-low",
+      "vendor": "claude",
+      "model": "claude-fable-5-1",
+      "effort": "low",
+      "reasoning": "adaptive",
+      "fallback": "default",
+      "aa_slug": "claude-fable-5-1-low",
+      "score": 48,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-fable-5-1-low"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-fable-5-1"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-fable-5",
+      "vendor": "claude",
+      "model": "claude-fable-5",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": "claude-opus-4-8",
+      "aa_slug": "claude-fable-5",
+      "score": 53,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-fable-5"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-fable-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-5",
+      "vendor": "claude",
+      "model": "claude-opus-5",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-5",
+      "score": 54,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-5"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-5-xhigh",
+      "vendor": "claude",
+      "model": "claude-opus-5",
+      "effort": "xhigh",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-5-xhigh",
+      "score": 53,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-5-xhigh"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-5-high",
+      "vendor": "claude",
+      "model": "claude-opus-5",
+      "effort": "high",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-5-high",
+      "score": 52,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-5-high"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-5-medium",
+      "vendor": "claude",
+      "model": "claude-opus-5",
+      "effort": "medium",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-5-medium",
+      "score": 50,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-5-medium"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-5-low",
+      "vendor": "claude",
+      "model": "claude-opus-5",
+      "effort": "low",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-5-low",
+      "score": 44,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-5-low"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-5",
+      "vendor": "claude",
+      "model": "claude-sonnet-5",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-sonnet-5",
+      "score": 45,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-sonnet-5"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-5-non-reasoning",
+      "vendor": "claude",
+      "model": "claude-sonnet-5",
+      "effort": "high",
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-sonnet-5-non-reasoning",
+      "score": 33,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-8",
+      "vendor": "claude",
+      "model": "claude-opus-4-8",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-8",
+      "score": 46,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-8"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-8"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-7",
+      "vendor": "claude",
+      "model": "claude-opus-4-7",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-7",
+      "score": 44,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-7"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-7"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-7-non-reasoning",
+      "vendor": "claude",
+      "model": "claude-opus-4-7",
+      "effort": "high",
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-7-non-reasoning",
+      "score": 35,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-7"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-6-adaptive",
+      "vendor": "claude",
+      "model": "claude-opus-4-6",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-6-adaptive",
+      "score": 36,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-6-adaptive"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-6",
+      "vendor": "claude",
+      "model": "claude-opus-4-6",
+      "effort": "high",
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-6",
+      "score": 31,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-6"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-5-thinking",
+      "vendor": "claude",
+      "model": "claude-opus-4-5",
+      "effort": null,
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-5-thinking",
+      "score": 34,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-5-thinking"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-opus-4-5",
+      "vendor": "claude",
+      "model": "claude-opus-4-5",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-opus-4-5",
+      "score": 28,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-opus-4-5"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-opus-4-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-4-6-adaptive",
+      "vendor": "claude",
+      "model": "claude-sonnet-4-6",
+      "effort": "max",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "aa_slug": "claude-sonnet-4-6-adaptive",
+      "score": 38,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-4-6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-4-6",
+      "vendor": "claude",
+      "model": "claude-sonnet-4-6",
+      "effort": "high",
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-sonnet-4-6",
+      "score": 29,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-sonnet-4-6"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-4-6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-4-6-non-reasoning-low-effort",
+      "vendor": "claude",
+      "model": "claude-sonnet-4-6",
+      "effort": "low",
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-sonnet-4-6-non-reasoning-low-effort",
+      "score": 27,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-4-6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-4-5-sonnet-thinking",
+      "vendor": "claude",
+      "model": "claude-sonnet-4-5",
+      "effort": null,
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "claude-4-5-sonnet-thinking",
+      "score": 29,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-4-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-4-5-sonnet",
+      "vendor": "claude",
+      "model": "claude-sonnet-4-5",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-4-5-sonnet",
+      "score": 23,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-4-5-sonnet"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-sonnet-4-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-4-5-haiku-reasoning",
+      "vendor": "claude",
+      "model": "claude-haiku-4-5",
+      "effort": null,
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "claude-4-5-haiku-reasoning",
+      "score": 22,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-haiku-4-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "claude/claude-4-5-haiku",
+      "vendor": "claude",
+      "model": "claude-haiku-4-5",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "claude-4-5-haiku",
+      "score": 17,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/claude-4-5-haiku"
+      ],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "claude-haiku-4-5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-8-flash",
+      "vendor": "gemini",
+      "model": "gemini-3.8-flash",
+      "effort": "high",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-8-flash",
+      "score": 47,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-8-flash-medium"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.8-flash-high"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-8-flash-medium",
+      "vendor": "gemini",
+      "model": "gemini-3.8-flash",
+      "effort": "medium",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-8-flash-medium",
+      "score": 47,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-8-flash-medium"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.8-flash-medium"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-8-flash-low",
+      "vendor": "gemini",
+      "model": "gemini-3.8-flash",
+      "effort": "low",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-8-flash-low",
+      "score": 42,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-8-flash-low"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.8-flash-low"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-7-flash",
+      "vendor": "gemini",
+      "model": "gemini-3.7-flash",
+      "effort": "high",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-7-flash",
+      "score": 45,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-7-flash"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.7-flash-high"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-7-flash-medium",
+      "vendor": "gemini",
+      "model": "gemini-3.7-flash",
+      "effort": "medium",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-7-flash-medium",
+      "score": 43,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-7-flash-medium"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.7-flash-medium"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-7-flash-low",
+      "vendor": "gemini",
+      "model": "gemini-3.7-flash",
+      "effort": "low",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-7-flash-low",
+      "score": 41,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-7-flash-low"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.7-flash-low"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "gemini/gemini-3-6-flash",
+      "vendor": "gemini",
+      "model": "gemini-3.6-flash",
+      "effort": "high",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-6-flash",
+      "score": 40,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-6-flash"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "gemini-3.6-flash-high"
+        ],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      }
+    },
+    {
+      "id": "grok/grok-4-6",
+      "vendor": "grok",
+      "model": "grok-4.6",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-6",
+      "score": 51,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-6"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-6-xhigh",
+      "vendor": "grok",
+      "model": "grok-4.6",
+      "effort": "xhigh",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-6-xhigh",
+      "score": 49,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-6-xhigh"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-6-medium",
+      "vendor": "grok",
+      "model": "grok-4.6",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-6-medium",
+      "score": 48,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-6-medium"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-6-low",
+      "vendor": "grok",
+      "model": "grok-4.6",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-6-low",
+      "score": 42,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-6-low"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.6"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-5",
+      "vendor": "grok",
+      "model": "grok-4.5",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-5",
+      "score": 45,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-5"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.5"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-3",
+      "vendor": "grok",
+      "model": "grok-4.3",
+      "effort": "high",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-3",
+      "score": 29,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-3"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.3"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-3-medium",
+      "vendor": "grok",
+      "model": "grok-4.3",
+      "effort": "medium",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-3-medium",
+      "score": 29,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-3-medium"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.3"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-3-low",
+      "vendor": "grok",
+      "model": "grok-4.3",
+      "effort": "low",
+      "reasoning": "reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-3-low",
+      "score": 29,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-3-low"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.3"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    },
+    {
+      "id": "grok/grok-4-3-non-reasoning",
+      "vendor": "grok",
+      "model": "grok-4.3",
+      "effort": null,
+      "reasoning": "non-reasoning",
+      "fallback": null,
+      "aa_slug": "grok-4-3-non-reasoning",
+      "score": 17,
+      "estimated": true,
+      "evidence_marker": "estimated",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/grok-4-3-non-reasoning"
+      ],
+      "evidence_report": "docs/reports/aa-grok-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [
+          "grok-4.3"
+        ],
+        "runtime_verified": false,
+        "reason": "AA evaluation identity is known; runtime transport identity has not been verified in this evidence snapshot"
+      }
+    }
+  ],
+  "unknown_configs": [
+    {
+      "id": "codex/gpt-5.6/unspecified/unspecified",
+      "vendor": "codex",
+      "model": "gpt-5.6",
+      "effort": null,
+      "reasoning": "unspecified",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "Generic model alias is not verified as Sol",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "codex/gpt-5.3-codex-spark/unspecified/unspecified",
+      "vendor": "codex",
+      "model": "gpt-5.3-codex-spark",
+      "effort": null,
+      "reasoning": "unspecified",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "No exact AA configuration found; GPT-5.3 Codex score is not transferable",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-codex-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-5/xhigh/adaptive",
+      "vendor": "claude",
+      "model": "claude-sonnet-5",
+      "effort": "xhigh",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "AA variant exists but Intelligence score unavailable in approved evidence",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-5/high/adaptive",
+      "vendor": "claude",
+      "model": "claude-sonnet-5",
+      "effort": "high",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "AA variant exists but Intelligence score unavailable in approved evidence",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-5/medium/adaptive",
+      "vendor": "claude",
+      "model": "claude-sonnet-5",
+      "effort": "medium",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "AA variant exists but Intelligence score unavailable in approved evidence",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "claude/claude-sonnet-5/low/adaptive",
+      "vendor": "claude",
+      "model": "claude-sonnet-5",
+      "effort": "low",
+      "reasoning": "adaptive",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "AA variant exists but Intelligence score unavailable in approved evidence",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-claude-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "gemini/gemini-3.6-flash/medium/unspecified",
+      "vendor": "gemini",
+      "model": "gemini-3.6-flash",
+      "effort": "medium",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "No separately verified AA score; do not reuse high score",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "gemini/gemini-3.6-flash/low/unspecified",
+      "vendor": "gemini",
+      "model": "gemini-3.6-flash",
+      "effort": "low",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "No separately verified AA score; do not reuse high score",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "gemini/gemini-3.1-pro/high/unspecified",
+      "vendor": "gemini",
+      "model": "gemini-3.1-pro",
+      "effort": "high",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "Reference-only Preview is not exact local high/low configuration",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    },
+    {
+      "id": "gemini/gemini-3.1-pro/low/unspecified",
+      "vendor": "gemini",
+      "model": "gemini-3.1-pro",
+      "effort": "low",
+      "reasoning": "unspecified",
+      "fallback": null,
+      "score": null,
+      "estimated": null,
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "status": "unknown",
+      "authority_eligible": false,
+      "reason": "Reference-only Preview is not exact local high/low configuration",
+      "source_urls": [],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "mapping_status": "unknown",
+      "transport_mapping": {
+        "status": "unknown",
+        "runtime_verified": false,
+        "resolved_config_id": null
+      }
+    }
+  ],
+  "reference_configs": [
+    {
+      "id": "gemini/gemini-3-1-pro-preview",
+      "vendor": "gemini",
+      "model": "gemini-3.1-pro-preview",
+      "effort": null,
+      "reasoning": "unspecified",
+      "fallback": null,
+      "aa_slug": "gemini-3-1-pro-preview",
+      "score": 37,
+      "estimated": false,
+      "evidence_marker": "unmarked",
+      "benchmark_version": "4.2",
+      "as_of": "2026-09-07",
+      "source_urls": [
+        "https://artificialanalysis.ai/models/comparisons/gemini-3-8-flash-vs-gemini-3-1-pro-preview"
+      ],
+      "evidence_report": "docs/reports/aa-gemini-evidence-2026-09-07.md",
+      "transport_mapping": {
+        "status": "unknown",
+        "candidate_model_ids": [],
+        "runtime_verified": false,
+        "reason": "Report establishes AA model/effort but not exact runtime transport or reasoning mode; unspecified is literal, not a wildcard"
+      },
+      "authority_eligible": false,
+      "reference_reason": "Proposal v2 retains this only as comparison; no local high/low mapping approved"
+    }
+  ],
+  "aliases": [
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-6-astra",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-6-astra",
+        "codex/gpt-6-astra-xhigh",
+        "codex/gpt-6-astra-high",
+        "codex/gpt-6-astra-medium",
+        "codex/gpt-6-astra-low",
+        "codex/gpt-6-astra-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.6-sol",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-5-6-sol",
+        "codex/gpt-5-6-sol-xhigh",
+        "codex/gpt-5-6-sol-high",
+        "codex/gpt-5-6-sol-medium",
+        "codex/gpt-5-6-sol-low",
+        "codex/gpt-5-6-sol-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.6-terra",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-5-6-terra",
+        "codex/gpt-5-6-terra-xhigh",
+        "codex/gpt-5-6-terra-high",
+        "codex/gpt-5-6-terra-medium",
+        "codex/gpt-5-6-terra-low",
+        "codex/gpt-5-6-terra-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.6-luna",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-5-6-luna",
+        "codex/gpt-5-6-luna-xhigh",
+        "codex/gpt-5-6-luna-high",
+        "codex/gpt-5-6-luna-medium",
+        "codex/gpt-5-6-luna-low",
+        "codex/gpt-5-6-luna-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.5",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-5-5",
+        "codex/gpt-5-5-high",
+        "codex/gpt-5-5-medium",
+        "codex/gpt-5-5-low",
+        "codex/gpt-5-5-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.4",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-5-4",
+        "codex/gpt-5-4-low",
+        "codex/gpt-5-4-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.4-mini",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "codex/gpt-5-4-mini",
+        "codex/gpt-5-4-mini-medium",
+        "codex/gpt-5-4-mini-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.6",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "codex",
+      "catalog_model": "gpt-5.3-codex-spark",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "default",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "best",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "fable",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "opus",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "sonnet",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "haiku",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "opus[1m]",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "sonnet[1m]",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "opusplan",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-fable-5",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-fable-5"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-fable-5-1",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-fable-5-1",
+        "claude/claude-fable-5-1-xhigh",
+        "claude/claude-fable-5-1-high",
+        "claude/claude-fable-5-1-medium",
+        "claude/claude-fable-5-1-low"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-opus-5",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-opus-5",
+        "claude/claude-opus-5-xhigh",
+        "claude/claude-opus-5-high",
+        "claude/claude-opus-5-medium",
+        "claude/claude-opus-5-low"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-sonnet-5",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-sonnet-5",
+        "claude/claude-sonnet-5-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-opus-4-8",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-opus-4-8"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-opus-4-7",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-opus-4-7",
+        "claude/claude-opus-4-7-non-reasoning"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-opus-4-6",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-opus-4-6-adaptive",
+        "claude/claude-opus-4-6"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-opus-4-5-20251101",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-sonnet-4-6",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-sonnet-4-6-adaptive",
+        "claude/claude-sonnet-4-6",
+        "claude/claude-sonnet-4-6-non-reasoning-low-effort"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-sonnet-4-5-20250929",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-haiku-4-5",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "claude/claude-4-5-haiku-reasoning",
+        "claude/claude-4-5-haiku"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "claude",
+      "catalog_model": "claude-haiku-4-5-20251001",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.8-flash-high",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-8-flash"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.8-flash-medium",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-8-flash-medium"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.8-flash-low",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-8-flash-low"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.7-flash-high",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-7-flash"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.7-flash-medium",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-7-flash-medium"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.7-flash-low",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-7-flash-low"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.6-flash-high",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "gemini/gemini-3-6-flash"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.6-flash-medium",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.6-flash-low",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.1-pro-high",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gemini-3.1-pro-low",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "claude-sonnet-4-6",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "claude-opus-4-6-thinking",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "gemini",
+      "catalog_model": "gpt-oss-120b-medium",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "grok",
+      "catalog_model": "grok-4.6",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [
+        "grok/grok-4-6",
+        "grok/grok-4-6-xhigh",
+        "grok/grok-4-6-medium",
+        "grok/grok-4-6-low"
+      ],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "Exact effort/reasoning/fallback and runtime transport verification required; candidates are not authorization",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "grok",
+      "catalog_model": "headroom-grok-build",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    },
+    {
+      "catalog_vendor": "grok",
+      "catalog_model": "grok-4.3-official",
+      "status": "unknown",
+      "resolved_config_id": null,
+      "candidate_config_ids": [],
+      "implicit_default_effort": null,
+      "runtime_verified": false,
+      "reason": "No proven exact AA transport mapping; floating, dated, cross-provider, or missing model identity remains unresolved",
+      "catalog_source": "scripts/configure.sh",
+      "source_kind": "local_catalog_not_runtime_identity"
+    }
+  ],
+  "coverage": {
+    "scored_configs": 78,
+    "reference_configs": 1,
+    "unknown_configs": 10,
+    "aliases": 47,
+    "by_vendor": {
+      "codex": 35,
+      "claude": 27,
+      "gemini": 7,
+      "grok": 9
+    }
+  },
+  "schema_notes": {
+    "estimated_false": "Unmarked in inspected evidence, not proof of complete independent measurement",
+    "reasoning_unspecified": "Evidence does not separately establish runtime reasoning selector; literal value, not wildcard",
+    "fallback_null": "Evidence does not specify a fallback; literal value, not permission to use any fallback",
+    "effort_null": "No AA effort label established for this reasoning configuration; do not fill with model maximum",
+    "candidate_config_ids": "Research cross-reference only; never authorize from an unresolved candidate",
+    "transport_mapping": "Live executor must verify exact vendor/model/effort/reasoning/fallback before evaluating score ceiling; all snapshot transports remain unverified",
+    "reference_configs": "Excluded from authority lookup"
+  }
+}